© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 428
    Prev
    Next
    INDEX
    Explanations

    class inheritance or method

    python-code · gemini-2.5-flash-lite

    def statement parameter (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĵ
    -0.18
    _h
    -0.16
    _ch
    -0.13
    he
    -0.12
    H
    -0.11
    h
    -0.11
     H
    -0.11
     h
    -0.11
     th
    -0.09
    ch
    -0.07
    POSITIVE LOGITS
    [j
    0.18
     j
    0.11
    j
    0.10
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    Activations Density 100.000%

    No Known Activations